Optimize LLM inference engines and serving architectures for production at scale.
Lead model and endpoint optimization initiatives across quantization, speculative decoding, KV-cache tuning, and distributed serving strategies. Work with kernel and platform teams to diagnose regressions, benchmark trade-offs between latency, throughput, memory, and cost, and deploy production improvements under real workloads. Requires deep hands-on experience with transformer inference stacks and distributed system architecture design.
Membership is €29/month, cancel anytime: every rate, every original listing link, and a daily alert for roles matching your filters.
Found at a specialist agency · listed 25 September 2026 · InsideJobs links you to the original posting.